Llama 3.1 405B
CoreWeave named first NVIDIA Exemplar Cloud for GB200 NVL72 training
CoreWeave says it is the first cloud provider named an NVIDIA Exemplar Cloud for training workloads on NVIDIA GB200 NVL72 systems. According to the company, its clusters…
Chips and infrastructureCoreWeave posts 800 TPS on Llama 3.1 405B in MLPerf with NVIDIA GB200
CoreWeave says it is the first cloud service provider to submit MLPerf Inference v5.0 results for NVIDIA GB200 Superchips, reaching 800 tokens per second (TPS) on the…
CoreWeave, NVIDIA and IBM Set MLPerf Record With 2,496-GPU Blackwell Cluster
CoreWeave, NVIDIA and IBM have delivered the largest MLPerf Training v5.0 submission ever recorded on NVIDIA Blackwell, using 2,496 GPUs. According to CoreWeave, the…
MLPerf Named Yardstick in EU AI Gigafactories Tender as Endpoints v1.0 Opens
MLPerf has been chosen as the performance standard for bids in the European Union's call for AI Gigafactories, according to MLCommons. The organization also said MLPerf…